© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13185
    Prev
    Next
    INDEX
    Explanations

    rock

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of “rock” (including “rock” subgenre terms like indie rock, punk‐rock, grunge, etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    	System
    -0.07
     Darwin
    -0.07
    amaz
    -0.07
     Bere
    -0.07
     Göz
    -0.07
     ostr
    -0.07
     شاخه
    -0.06
     stap
    -0.06
    Lewis
    -0.06
     exited
    -0.06
    POSITIVE LOGITS
    _TM
    0.07
    句
    0.07
     karşılık
    0.07
     vu
    0.07
     фун
    0.06
    '){
↵
    0.06
    .Navigator
    0.06
    industry
    0.06
    (cb
    0.06
    677
    0.06
    Activations Density 0.008%

    No Known Activations